def get_graph(*, _limit=(), _print=()):
return bonobo.Graph(
bonobo.FileReader('datasets/passwd.txt'),
skip_comments,
*_limit,
lambda s: s.split(':')[0],
*_print,
bonobo.FileWriter('usernames.txt', fs='fs.output'),
)
def get_graph(*, _limit=(), _print=()):
return bonobo.Graph(
bonobo.FileReader("passwd.txt", fs="fs.static"),
skip_comments,
*_limit,
lambda s: s.split(":")[0],
*_print,
bonobo.FileWriter("usernames.txt", fs="fs.output"),
)
def get_cs_graph(**options):
"""
This function builds the graph that needs to be executed.
:return: bonobo.Graph
"""
graph = bonobo.Graph()
split_employees = bonobo.noop
graph.add_chain(bonobo.FileReader(path='HrExport.txt',
fs='centerstone',
encoding='latin-1',
eol="\r\n"),
split_tabs,
prefix_desk_ids,
join_wpr,
mismatch,
split_employees,
_name="main")
# Process regular employees
if options['dry_run']:
update = ()
else:
update = (update_employee_record, )
graph.add_chain(bonobo.PrettyPrinter(),
*update,
bonobo.PrettyPrinter(),
_input=split_employees)
# Dump out outlier employees
#graph.add_chain(
# bonobo.Filter(filter=odd_employee),
# bonobo.UnpackItems(0),
# bonobo.PrettyPrinter(),
# _input=split_employees)
#
return graph
import bonobo
def split_one(line):
return line.split(', ', 1)
graph = bonobo.Graph(
bonobo.FileReader('coffeeshops.txt'),
split_one,
bonobo.JsonWriter('coffeeshops.json'),
)
if __name__ == '__main__':
bonobo.run(graph, services={'fs': bonobo.open_examples_fs('datasets')})
import bonobo
from bonobo.commands.run import get_default_services
def skip_comments(line):
if not line.startswith('#'):
yield line
graph = bonobo.Graph(
bonobo.FileReader('datasets/passwd.txt'),
skip_comments,
lambda s: s.split(':'),
lambda l: l[0],
print,
)
if __name__ == '__main__':
bonobo.run(graph, services=get_default_services(__file__))
import os
import pathlib
import bonobo
workdir = pathlib.Path(os.path.dirname(__file__))
graph = bonobo.Graph(
bonobo.FileReader(path=workdir.joinpath('datasets/coffeeshops.txt')),
print,
)
if __name__ == '__main__':
bonobo.run(graph)
